基本信息

---

下载

   友情提示：（无需注册或充值，赞助后即可获取资源下载链接）

---

     嘿，亲！知识可是无价之宝呢，但咱这精心整理的资料也耗费了不少心血呀。小小地破费一下，绝对物超所值哦！如有下载和支付问题，请联系我们QQ(微信同号)：813200300

本次赞助数额为： 2 元　

支付宝支付

微信支付

   源码介绍

---

用python提取小说主要人物关系

# -*-  coding: utf-8 -*- import os, sys import jieba, codecs, math import jieba.posseg as pseg
names = {} # 姓名字典 relationships = {} # 关系字典 lineNames = [] # 每段内人物关系 jieba.load_userdict("dict.txt") # 加载字典 with codecs.open("busan.txt", "r", "utf8") as f: for line in f.readlines():
        poss = pseg.cut(line) # 分词并返回该词词性  lineNames.append([]) # 为新读入的一段添加人物名称列表  for w in poss: if w.flag != "nr" or len(w.word) < 2: continue # 当分词长度小于2或该词词性不为nr时认为该词不为人名  lineNames[-1].append(w.word) # 为当前段的环境增加一个人物  if names.get(w.word) is None:
                names[w.word] = 0  relationships[w.word] = {}
            names[w.word]  = 1 # 该人物出现次数加 for line in lineNames: # 对于每一段  for name1 in line: for name2 in line: # 每段中的任意两个人  if name1 == name2: continue  if relationships[name1].get(name2) is None: # 若两人尚未同时出现则新建项  relationships[name1][name2]= 1  else:
                relationships[name1][name2] = relationships[name1][name2] 1 # 两人共同出现次数加 1 with codecs.open("busan_node.txt", "w", "gbk") as f:
    f.write("Id Label Weight\r\n") for name, times in names.items():
        f.write(name " "  name " "  str(times) "\r\n") with codecs.open("busan_edge.txt", "w", "gbk") as f:
    f.write("Source Target Weight\r\n") for name, edges in relationships.items(): for v, w in edges.items(): if w > 3:
                f.write(name " "  v " "  str(w) "\r\n")